© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59928
    Prev
    Next
    INDEX
    Explanations

    fluid/airflow/flow descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ĩåŃķ
    -0.08
    人å¤ļ
    -0.08
    æĮ¯åįİ
    -0.08
     Frucht
    -0.08
     bergen
    -0.07
    åħ±æµİ
    -0.07
    åľĪçļĦ
    -0.07
    éľ
    -0.07
    é¦
    -0.07
    äºķä¸ĭ
    -0.07
    POSITIVE LOGITS
     flutter
    0.09
     lamin
    0.08
    èĻ±
    0.08
     aero
    0.07
    å¼Ģ设äºĨ
    0.07
     airflow
    0.07
    æł½
    0.07
     profil
    0.07
    çĹĴ
    0.07
    nesc
    0.07
    Activations Density 0.001%

    No Known Activations